Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 56061
    Prev
    Next
    INDEX
    Explanations

    mathematical conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     presso
    -0.09
     लॉक
    -0.08
     Lock
    -0.08
     ட
    -0.08
     chiar
    -0.08
    Kort
    -0.08
    .lock
    -0.08
     ബ്ല
    -0.08
    Lock
    -0.08
    -ticket
    -0.08
    POSITIVE LOGITS
     stretch
    0.08
    stretch
    0.08
     typically
    0.08
     depende
    0.07
    ,当
    0.07
     nuance
    0.07
    typically
    0.07
     equival
    0.07
     rupa
    0.07
     sederhana
    0.07
    Activations Density 0.132%

    No Known Activations